Abstract. Brain Computer Interface (BCI) systems, which are based on motor imagery, enable humans to command arti cial peripherals by merely thinking about the task. There is a tremendous interest in implementing BCIs on portable platforms, such as Field Programmable Gate Arrays (FPGAs) due to their low-cost, low-power and portability characteristics. This article presents the design and implementation of a Brain Computer Interface (BCI) system based on motor imagery on a Virtex-6 FPGA. In order to design an accurate algorithm, the proposed method avails statistical learning methods such as Mutual Information (MI), Linear Discriminant Analysis (LDA), and Support Vector Machine (SVM). It also uses Separable Common Spatio Spectral Pattern (SCSSP) method in order to extract features. Simulation results prove achieved performances of 73.54% for BCI competition III-dataset V, 67.2% for BCI competition IV-dataset 2a with all four classes, 80.55% for BCI competition IV-dataset 2a with the rst two classes, and 81.9% for captured signals. Moreover, the nal reported hardware resources determine its e ciency as a result of using retiming and folding techniques from the VLSI architecture' perspective. The complete proposed BCI system achieves not only excellent recognition accuracy, but also remarkable implementation e ciency in terms of portability, power, time, and cost.
The brain-computer interfacing (BCI), a platform to extract features and classify different motor movement tasks from noisy and highly correlated electroencephalogram signals, is limited mostly by the complex and power-hungry algorithms. Among different techniques recently devised to tackle this issue, real-time onset detection, due to its negligible delay and minimal power overhead, is the most efficient one. Here, we propose a novel algorithm that outperforms the state-of-the-art design by sixfold in terms of speed, without sacrificing the accuracy for a real-time, hand movement intention detection based on the adaptive wavelet transform with only 1 s detection delay and maximum sensitivity of 88% and selectivity of 78% (only 7% loss of sensitivity).
The outlook of brain-computer interfacing (BCI) is very bright. The real-time, accurate detection of a motor movement task is critical in BCI systems. The poor signal-to-noise-ratio (SNR) of EEG signals and the ambiguity of noise generator sources in brain renders this task quite challenging. In this paper, we demonstrate a novel algorithm for precise detection of the onset of a motor movement through identification of event-related-desynchronization (ERD) patterns. Using an adaptive matched filter technique implemented based on an optimized continues Wavelet transform by selecting an appropriate basis, we can detect single-trial ERDs. Moreover, we use a maximum-likelihood (ML), electrooculography (EOG) artifact removal method to remove eye-related artifacts to significantly improve the detection performance. We have applied this technique to our locally recorded Emotiv(®) data set of 6 healthy subjects, where an average detection selectivity of 85 ± 6% and sensitivity of 88 ± 7.7% is achieved with a temporal precision in the range of -1250 to 367 ms in onset detections of single-trials.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.